Layer-wise analysis of self-supervised pre-trained speech representations

Syllable Segmentation and Cross-Lingual Generalization in a Visually Grounded, Self-Supervised Speech Model

Code and data release for the paper "Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignment" (NeurIPS 2023)

Word Discovery in Visually Grounded, Self-Supervised Speech Models

Public Code for the paper MAE-AST: Masked Autoencoding Audio Spectrogram Transformer

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Code for experiments in text watermarking and lexical substitution

The Stanford Word Substitution (Swords) Benchmark